Read news on alignment with our app.
Read more in the app
Talent Is Alignment
Center for the Alignment of AI Alignment Centers
This researcher turned OpenAI’s open weights model gpt-oss-20b into a non-reasoning ‘base’ model with less alignment, more freedom
Data everywhere, alignment nowhere: What dashboards are getting wrong, and why you need a data product manager
LLM's Illusion of Alignment
Extreme Super-Resolution via Scale Autoregression and Preference Alignment
Alignment is not free: How model upgrades can silence your confidence signals
Alignment faking in large language models
Takes on "Alignment Faking in Large Language Models"
Productivity Versus Alignment
StarCoder2-Instruct: Transparent Self-Alignment for Code Generation